Wasserstein loss
One of the loss functions commonly used in generative adversarial networks, based on the earth mover's distance between the distribution of generated data and real data.
Plain English Explanation
One of the loss functions commonly used in generative adversarial networks, based on the earth mover's distance between the distribution of generated data and real data.
How is it used?
Practitioners refer to wasserstein loss when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.